GPT-6 Luna

GPT-6 Luna is the smallest and cheapest tier of OpenAI's GPT-6 generation. It keeps the 1M-token context window, takes text and images, and supports function calling and structured outputs, at a price built for volume: classification, extraction, routing, summaries and high-traffic chat. Reasoning tokens bill as output. Move up to Sol or Astra when a task needs deeper reasoning.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-6-luna",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)